← Models

Meta · current

Llama 3.3 70B Instruct fp8 Fast

Llama 3.3 70B Instruct fp8 Fast is attributed to Meta in the catalog. It accepts text input and produces text output. Reported capabilities include tool calling.

Compare model

Modalities

Hosted provider token rates

$0.293 / $2.253

USD per 1M input / output tokens · Cloudflare Workers AI

Context

24K

Released

2024-12-06

Knowledge cutoff

Dec 2023

No recent lab-operated provider rate is available. Showing the third-party host with the lowest input rate + ¼ output rate. This is one offering, not an average; other providers, modalities, tiers, and fees may differ.

Where to use it

1 observed offerings · token prices in USD per million where available

Estimate your workload cost
Cloudflare Workers AI

@cf/meta/llama-3.3-70b-instruct-fp8-fast

current

Input

$0.293

Output

$2.253

Cache

—

Context

24K

Max output

24K
Reasoning
No
Tool calling
Yes
Structured output
No
Temperature
Yes

Recent price

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Capabilities and limits

Input
text
Output
text
Max output
24K
Weights
Open (source-reported)
Release
2024-12-06
Knowledge cutoff
Dec 2023
Family
llama

Tool calling

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Models to compare

Candidates match reported specifications; they are not tested replacements.

Model and price history

Latest recorded change: source refresh · 2026-10-12

Model changes (1)
  • source refresh · 2026-10-12
    {
      "before": {
        "knowledge_cutoff_reported": null
      },
      "after": {
        "knowledge_cutoff_reported": "2023-12"
      }
    }
Price history (40 observations)
DateProviderInput / output
2026-11-02Cloudflare Workers AI$0.293 / $2.253
2026-11-01Cloudflare Workers AI$0.293 / $2.253
2026-10-31Cloudflare Workers AI$0.293 / $2.253
2026-10-30Cloudflare Workers AI$0.293 / $2.253
2026-10-29Cloudflare Workers AI$0.293 / $2.253
2026-10-28Cloudflare Workers AI$0.293 / $2.253
2026-10-27Cloudflare Workers AI$0.293 / $2.253
2026-10-27Cloudflare Workers AI$0.293 / $2.253
2026-10-27Cloudflare Workers AI$0.293 / $2.253
2026-10-27Cloudflare Workers AI$0.293 / $2.253
2026-10-26Cloudflare Workers AI$0.293 / $2.253
2026-10-25Cloudflare Workers AI$0.293 / $2.253
2026-10-24Cloudflare Workers AI$0.293 / $2.253
2026-10-24Cloudflare Workers AI$0.293 / $2.253
2026-10-24Cloudflare Workers AI$0.293 / $2.253
2026-10-23Cloudflare Workers AI$0.293 / $2.253
2026-10-23Cloudflare Workers AI$0.293 / $2.253
2026-10-23Cloudflare Workers AI$0.293 / $2.253
2026-10-23Cloudflare Workers AI$0.293 / $2.253
2026-10-23Cloudflare Workers AI$0.293 / $2.253
2026-10-22Cloudflare Workers AI$0.293 / $2.253
2026-10-21Cloudflare Workers AI$0.293 / $2.253
2026-10-20Cloudflare Workers AI$0.293 / $2.253
2026-10-19Cloudflare Workers AI$0.293 / $2.253
2026-10-18Cloudflare Workers AI$0.293 / $2.253
2026-10-17Cloudflare Workers AI$0.293 / $2.253
2026-10-12Cloudflare Workers AI$0.293 / $2.253
2026-10-12Cloudflare Workers AI$0.293 / $2.253
2026-10-11Cloudflare Workers AI$0.293 / $2.253
2026-10-10Cloudflare Workers AI$0.293 / $2.253
2026-10-09Cloudflare Workers AI$0.293 / $2.253
2026-10-09Cloudflare Workers AI$0.293 / $2.253
2026-10-08Cloudflare Workers AI$0.293 / $2.253
2026-10-07Cloudflare Workers AI$0.293 / $2.253
2026-09-22Cloudflare Workers AI$0.293 / $2.253
2026-09-21Cloudflare Workers AI$0.293 / $2.253
2026-09-20Cloudflare Workers AI$0.293 / $2.253
2026-09-19Cloudflare Workers AI$0.293 / $2.253
2026-09-18Cloudflare Workers AI$0.293 / $2.253
2026-09-17Cloudflare Workers AI$0.293 / $2.253